no code implementations • 7 Feb 2024 • Wanli Ma, Oktay Karakus, Paul L. Rosin
The proposed semi-supervised learning-based knowledge distillation (SSLKD) approach demonstrates a notable improvement in the performance of the student model, in the application of road segmentation, surpassing the effectiveness of traditional semi-supervised learning methods.
no code implementations • 22 Nov 2023 • Wanli Ma, Oktay Karakus, Paul L. Rosin
The two proposed methods of DiverseNet, namely the DiverseHead and DiverseModel, achieve the highest semantic segmentation performance in four widely utilised remote sensing imagery data sets compared to state-of-the-art semi-supervised learning methods.
no code implementations • 17 May 2023 • Wanli Ma, Oktay Karakus, Paul L. Rosin
Especially in the application of land cover classification, pixel-level manual labelling in large-scale imagery is labour-intensive, time-consuming and expensive.
no code implementations • 11 Oct 2022 • Henry Booth, Wanli Ma, Oktay Karakus
As such, this paper comprised of three main components: (1) the development of a machine learning model, (2) the construction of the MAP-Mapper, an automated tool for mapping marine-plastic density, and finally (3) an evaluation of the whole system for out-of-distribution test locations.
no code implementations • 11 Dec 2020 • Wanli Ma, Alin Achim, Oktay Karakuş
In this paper, we analyse synthetic aperture radar (SAR) images of the sea surface using an inverse problem formulation whereby Radon domain information is enhanced in order to accurately detect ship wakes.
no code implementations • NeurIPS 2014 • Adams Wei Yu, Wanli Ma, YaoLiang Yu, Jaime Carbonell, Suvrit Sra
We study the problem of finding structured low-rank matrices using nuclear norm regularization where the structure is encoded by a linear map.